Small Target Segmentation Method in Complex Background Based on Attention Mechanism

Abstract

Aiming at the problem that the accuracy of small target segmentation is not high in complex scenes, this paper proposes a target segmentation method based on attention mechanism. The convolutional neural network extract the feature maps based on VGG16, and extract multi directional feature as the horizontal and vertical feature maps in low layer networks, which can effectively fuse and enrich the context information. Moreover, combined with the attention mechanism, the relationship between the channels of feature maps is learned adaptively. The useful information is emphasized, and the redundant information is suppressed. The discrimination ability of feature maps is improved. The enhanced feature maps are then used for segmentation. The experimental results show that, compared with similar algorithms, the proposed algorithm has better segmentation effect for most small targets and significantly improves the segmentation accuracy.